Speech Synthesis (S^2)
===

Speech synthesis with fairseq.

- Autoregressive and non-autoregressive models
- Multi-speaker synthesis
- Audio preprocessing
- Automatic metrics
- Similar data configuration as [S2T](../speech_to_text/README.md)


## Examples
- [Single-speaker synthesis on LJSpeech](docs/ljspeech_example.md)
- [Multi-speaker synthesis on VCTK](docs/vctk_example.md)
- [Multi-speaker synthesis on Common Voice](docs/common_voice_example.md)